We are delighted to welcome Prof. Simon Olsson to the Atomistic Modeling Seminar series and are looking forward to his upcoming talk on generative molecular dynamics!

Prof. Simon Olsson is Associate Professor of Artificial Intelligence in the Natural Sciences at Chalmers University of Technology in Gothenburg, Sweden, where he has held a faculty position since 2020. He is a WASP AI/MLX Professor, WASP Fellow, and member of ELLIS. His research develops machine learning methods for molecular simulation and statistical mechanics, with applications in drug discovery, vaccine design, and materials science. He is the recipient of numerous prestigious grants and awards including an ERC Consolidator Grant and the inaugural ICTP-IBM Brahmagupta AI Prize.

In his talk, “Generative Molecular Dynamics”, Prof. Olsson will discuss molecular dynamics as an important tool across chemistry, physics, and biology, while also addressing the practical limitations posed by the sampling problem. He will present Generative Molecular Dynamics as a strategy to efficiently generate independent statistics through the training of generative machine learning models. The talk will further outline recent work on implicit transfer operators and ongoing efforts to generalize this principle.

Date: Tuesday, May 26, 2026, 10:30 am

Location: MIBE Lecture Hall

Abstract:

Molecular dynamics (MD) is an important tool across chemistry, physics, and biology. MD connects microscopic physics to macroscopic thermodynamic observables yet is often practically limited by the sampling problem. Computing thermodynamic observables — free energies and rates— requires the sampling of statistics from high-dimensional molecular probability distributions to form unbiased averages and correlations — without a sufficient sample the link is lost.

In this talk, the advent of Generative Molecular Dynamics [1] will be discussed as a strategy to efficiently generate independent statistics through the training of generative machine learning models. Recent work including implicit transfer operators [2], as well as efforts to generalize this principle [3,4], will also be outlined. 

[1] Olsson “Generative Molecular dynamics” Current Opinion in Structural Biology 96, 103213
[2] Schreiner et al “Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics” Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
[3] Diez et al. “Transferable Generative Models Bridge Femtosecond to Nanosecond Time- Step Molecular Dynamics” Science Advances (2026)
[4] Antoniadis et al. “Protein Language Model Embeddings Improve Generalization of Implicit Transfer Operators” ICML2026